Autonomous Development

The Ralph Workflow

An autonomous coding agent that solves the AI context window problem through external memory and atomic task execution.

The Solution: External Memory

AGENTS.md

Project-wide context document that any AI can read to understand:

  • • Tech stack and conventions
  • • File structure patterns
  • • Code style guidelines
  • • Security requirements
  • • Testing standards

progress.txt

Iteration history that tracks:

  • • Completed tasks
  • • Current iteration number
  • • Blockers encountered
  • • Decisions made
  • • Files modified

How Ralph Works

1

Read Context

Ralph reads AGENTS.md and progress.txt to understand the project and what's been done

2

Pick One Task

Selects the next uncompleted task from PRD.md (sized for ~10 minutes of work)

3

Execute Task

Implements the task following project patterns in AGENTS.md

4

Update Progress

Marks task complete in progress.txt with notes on what was done

5

Loop or Exit

Either continues to next task or exits for human review

Atomic Task Design

Each task in PRD.md must be atomic—completable in ~10 minutes without dependencies:

❌ Bad Task

"Build the user dashboard with charts, settings, and profile management"

✓ Good Tasks

• Create dashboard layout component

• Add revenue chart molecule

• Build settings form organism

• Implement profile avatar upload

Running Ralph

Unix/Mac (Bash)

chmod +x ralph.sh
./ralph.sh

Windows (PowerShell)

.\ralph.ps1

Key Benefits

Persistent Memory

Context survives across sessions via external files

Consistent Output

Atomic tasks produce complete, tested code every time

Pattern Adherence

AGENTS.md ensures uniform code style across iterations

Looking for More Structure?

GSD (Get Shit Done) takes Ralph's fundamentals and packages them into a more structured, spec-driven workflow with multi-agent orchestration and automatic verification.